Search Results for author:
Found 11 papers, 2 papers with code
From Large to Small Datasets: Size Generalization for Clustering Algorithm Selection
We approach this problem by introducing a notion of size generalization for clustering algorithm accuracy.
On Scrambling Phenomena for Randomly Initialized Recurrent Networks
Recurrent Neural Networks (RNNs) frequently exhibit complicated dynamics, and their sensitivity to the initialization process often renders them notoriously hard to train.
Efficiently Computing Nash Equilibria in Adversarial Team Markov Games
In this work, we depart from those prior results by investigating infinite-horizon \emph{adversarial team Markov games}, a natural and well-motivated class of games in which a team of identically-interested players -- in the absence of any explicit coordination or communication -- is competing against an adversarial player.
Expressivity of Neural Networks via Chaotic Itineraries beyond Sharkovsky's Theorem
Given a target function $f$, how large must a neural network be in order to approximate $f$?
From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clustering
Recently, Dasgupta reframed HC as a discrete optimization problem by introducing a global cost function measuring the quality of a given tree.
Better Depth-Width Trade-offs for Neural Networks through the lens of Dynamical Systems
The expressivity of neural networks as a function of their depth, width and type of activation units has been an important question in deep learning theory.
Depth-Width Trade-offs for ReLU Networks via Sharkovsky's Theorem
Motivated by our observation that the triangle waves used in Telgarsky's work contain points of period 3 - a period that is special in that it implies chaotic behavior based on the celebrated result by Li-Yorke - we proceed to give general lower bounds for the width needed to represent periodic functions as a function of the depth.
Adversarially Robust Low Dimensional Representations
In particular, our adversarially robust PCA primitive leads to computationally efficient and robust algorithms for both unsupervised and supervised learning problems such as clustering and learning adversarially robust classifiers.
Hierarchical Clustering better than Average-Linkage
Hierarchical Clustering (HC) is a widely studied problem in exploratory data analysis, usually tackled by simple agglomerative procedures like average-linkage, single-linkage or complete-linkage.
On the Computational Power of Online Gradient Descent
We prove that the evolution of weight vectors in online gradient descent can encode arbitrary polynomial-space computations, even in very simple learning settings.
Hierarchical Clustering with Structural Constraints
For many real-world applications, we would like to exploit prior information about the data that imposes constraints on the clustering hierarchy, and is not captured by the set of features available to the algorithm.
